Using dual?polarization GPS antenna with optimized adaptive neuro?fuzzy inference system to improve single point positioning accuracy in urban canyons

Abstract This paper builds on the machine learning research to propose two new algorithms based optimizing Adaptive Neuro Fuzzy Inference System (ANFIS) with a dual-polarization antenna predict pseudorange errors by considering multiple variables including right-hand circular polarized (RHCP) signal strength, strength difference between left-hand (LHCP) and RHCP outputs, satellites’ elevation angle, residuals. The final position is calculated following application of predicted correct for effects non-line-of-sight (NLOS) multipath reception. results show that proposed algorithm in 30% improvement root mean square error (RMSE) 2D (horizontal) component static applications when training testing data are collected at same location. corresponds 13% 20% from locations away dataset.